فصلنامه سنجش از دور و GIS ایران
سال شانزدهم شماره 2 (پیاپی 62، تابستان 1403)

Due to its environmental diversity, Iran ranks high in terms of crises caused by natural disasters. Flooding, as one of these disasters, is  causing severe social, economic, health, and environmental damage in many areas due to rapid urban growth and climate change. Therefore spatial forecasting of floods is crucial, as failure to identify flood risk areas in a catchment can exacerbate the destructive effects of floods. Recent advances in remote sensing, geographic information systems, machine learning, and statistical modelling have made it possible to produce highly accurate flood prediction maps. This study aims to predict flood risk areas in the Karun watershed using Sentinel satellite images and a novel ensemble approach with six machine learning models.

In this study, Synthetic Aperture Radar (SAR) data from Sentinel-1 images were used to identify areas affected by flooding.  First, the dates of heavy rainfall and flooding events in the study area were identified from various sources of information. Subsequently, Sentinel-1 images were obtained from the Copernicus database, representing the area before and after the flood events. The aforementioned data were processed using the SNAP platform. The identification of flood-affected areas was achieved through the application of the thresholding technique. For this purpose, the Normalized Difference Water Index (NDWI) generated from Sentinel-2 images and land cover classes indicating permanent water bodies were employed to determine the threshold for identifying flood-affected areas. The flood polygon layer was converted to a point layer, resulting in a total of 70 flood occurrence points. A review of previous studies and local characteristics identified seven main factors that significantly affect flood occurrence in the region. These factors include the Normalized Difference Vegetation Index (NDVI), Topographic Wetness Index (TWI), slope, flow direction, flow accumulation, distance from the river, and monthly rainfall. Additionally, the Digital Elevation Model (DEM) of the region was obtained from the SRTM database, and the spatial resolution of all factors was aligned with the DEM layer. Subsequently, various machine learning algorithms were employed to develop a combined model that provides more accurate predictions of flood-prone areas. The individual models include the Generalized Linear Model (GLM), Boosted Regression Tree (BRT), Support Vector Machine (SVM), Random Forest (RF), Multivariate Adaptive Regression Splines (MARS), and Maximum Entropy (MAXENT).                    

The results of this study indicate that the northeast of Aligudarz city, parts of Durud and Azna in Lorestan province, Khademmirza, Shahrekord, and Kiyar in Chaharmahal Bakhtiari province, Dana and Boyer Ahmad in Kohgiluyeh and Boyer Ahmad province, Semirom city in Isfahan province, and the southern border areas of Karun River in Khuzestan province have the highest flood potential in this basin. The performance evaluation of the models revealed that the Random Forest (RF) and Maximum Entropy (MaxEnt) models exhibited the highest accuracy among the individual models. These models, by combining environmental information and flood occurrence data, can produce highly accurate flood susceptibility maps. These maps can serve as crucial management tools to mitigate the adverse effects of floods and prevent development in vulnerable areas.

Overall, this study demonstrates that the use of an ensemble approach which combines machine learning models can provide more reliable results in the prediction of flood risk areas. The findings of this research are beneficial for managers and planners, as they can prevent development in vulnerable areas and consequently help reduce financial losses and human damages in the future.

Agriculture serves as the cornerstone of the global economy, providing the main source of food and raw materials for various industries. However, the rising demand for food as a consequence of population growth represents a considerable threat to food security, particularly in light of the limited access to freshwater resources. It is noteworthy that agriculture alone consumes about 70% of the world's freshwater resources, thereby emphasizing the critical need to manage and enhance irrigation efficiency to ensure sustainable food production. Therefore, the management and enhancement of irrigation efficiency are essential. At the core of determining irrigation water requirements lies the concept of actual crop evapotranspiration (ETa), which represents the combined water loss from soil evaporation and plant transpiration. Accurate estimation of ETa is crucial in optimizing irrigation methods, maximizing crop yield, and minimizing water consumption. Various models and tools have been developed to estimate ETa, aiming to provide more user-friendly and efficient methods for farmers and researchers. Given the extensive application of ET estimation models, there is a clear need to focus on the development of accurate and efficient methods for determining this parameter. Thus, this study aims to compare user-friendly ETa estimation methods, including the EEFLUX system, the METRICTOOL tool, and the automatic hot and cold pixel selection method of the SEBAL and METRIC models.

The Earth Engine Evapotranspiration Flux (EEFLUX) is a version of the METRIC model that operates on the Google Earth Engine platform. METRICTOOL is a new tool in ArcGIS based on the METRIC model, offering enhanced pre-processing capabilities and automatic data identification. This tool reduces computation time by 50% and provides a user-friendly alternative to other existing METRIC model implementation platforms. The automatic hot and cold pixel selection method involves creating a binary map of eligible pixels using a rule-based classifier and a comprehensive search algorithm to identify hot and cold pixels based on defined criteria. To estimate ET using these methods, six Landsat 8 satellite images were utilized during the winter wheat crop planting period at Tehran University farms in Mohammadshahr Karaj. The evaluation of these methods was conducted using alfalfa reference evapotranspiration (ETr) calculated with the FAO-Penman-Monteith method as reference data.

The Root Mean Square Error (RMSE) values for the EEFLUX system, METRICTOOL, SEBAL, and automatic METRIC tools were determined as 2.45, 0.33, 0.39, and 2.76, respectively. Despite numerical differences, the evaporation and transpiration product of the EEFLUX system showed significant correlations with other methods. For instance, the R2 between ETa estimates from the EEFLUX system and the METRICTOOL tool was found to be 0.91. Although the data from the EEFLUX system may not be precise enough for local studies due to the use of CFSV2 global meteorological data in Iran, they yield acceptable results in large or global-scale studies. The METRICTOOL tool and automatic METRIC model exhibited the highest correlation (R2=0.99) and numerical agreement with each other, with RMSE values of 0.33 and 0.39, respectively, indicating higher accuracy compared to the automatic SEBAL model.

The results of the numerical analysis indicate that the automatic hot and cold pixel selection approach can achieve similar accuracy to that of the METRICTOOL tool. This automated approach enhances the efficiency of the model in terms of time and effectiveness, reducing the potential for human error in estimating evapotranspiration for new or inexperienced users, and making these models accessible to the public. Furthermore, EEFLUX data can be utilised for the implementation of management measures in large-scale studies.

In recent years, the use of hyperspectral imagery in various fields of Earth science, especially in remote sensing, has significantly increased due to its rich spectral information. However, the classification of these images and the extraction of useful information from them present variues challenges. These challenges include the effective management of high-dimensional data and the achievement of accurate classification when the number of training samples is limited. One of the primary objectives of the remote sensing scientific community has been to improve the accuracy of image classification, thereby facilitating comprehensive investigations of surface phenomena and changes. In recent years, there has been a growing interest in the use of spatial features as a means of improving the classification accuracy of hyperspectral images. Numerous methods have been suggested for the spectral-spatial classification of hyperspectral images. Currently, research is being conducted with the objective of developing simpler yet more accurate methodologies. The existence of intricate relationships between different bands of the hyperspectral image, as evidenced by research in the field of machine vision, has prompted the development of a novel methodology in current research for modelling the complex relationships between spectral and spatial features within a hyperspectral image. The main objective of this article is to present a novel and efficient approach that combines features derived from weighted local kernel matrices of spectral and fractal characteristics for hyperspectral image classification.

 In the present research, hyperspectral images are first subjected to a dimension reduction step. Subsequently, spatial features are generated based on the directional fractal dimension, and these features are further reduced in dimension. In the subsequent stage, the novel features are derived from the weighted local kernel matrices of both the spectral and fractal feature groups. These secondary features consider nonlinear local dependencies between spectral and fractal characteristics, which were not previously considered in other feature generation methods. Ultimately, this stage serves to enhance the accuracy of the classification process. The resulting feature vectors from both groups are then merged, creating a comprehensive vector that is rich in spectral-spatial information for each pixel. Finally, the support vector machine (SVM) algorithm is employed to classify the obtained feature vector and assign labels to each pixel. The experiments conducted as part of this research were carried out on two real hyperspectral benchmark images: one depicting Indian pine and the other the University of Pavia.

The analysis of the outcomes demonstrates the effectiveness of the proposed approach, which incorporates features derived from weighted local kernel matrices of both spectral and fractal characteristics. The classification accuracy of both the Indian Pine and University of Pavia images is enhanced by 20% and 18%, respectively, compared to the exclusive use of spectral features. These findings confirm that incorporating spatial information significantly enhances classification accuracy, particularly in scenarios with limited training samples. Furthermore, the results demonstrate that the proposed method exhibits superior accuracy compared to other studies conducted in this domain.

The enhanced performance of the proposed method in comparison to other competitors can be attributed to the incorporation of local non-linear dependencies between both spectral and fractal features, which have not been considered in previous studies. In the future, further improvements to the proposed approach are anticipated. Firstly, efforts will be made to optimise the efficiency of the proposed method in terms of processing time. Furthermore, the accuracy of the method will be enhanced by considering additional fractal features in subsequent steps. These refinements will be pursued in future research endeavours.

Recently, the use of big data from mobile devices has received considerable attention in transportation studies. The need to do activities is the main inducement for urban trip generation. Furthermore, urban activities and their patterns vary both over space and time. Mobile phone data, as a kind of continuous spatiotemporal data, records the location of people at different times. Therefore such data is suitable for the estimation of urban activity levels and the detection of patterns. In this study, we selected Shiraz as the study area due to its cultural, religious, and tourist significance, as well as the presence of major healthcare centres in the city. The analysis of spatial and temporal patterns of urban trips using continuous spatiotemporal data, such as mobile phone records, can significantly contribute to the improvement of transportation system management, planning, and policy-making for Shiraz.

The variable under investigation in this study is the activity density within a specific time interval and a defined spatial unit. Activity is defined as the number of individuals who either enter or leave a specific area for a specific purpose. Furthermore, activity density indicates the level of activity within the area’s unit of measurement. To investigate activity density across 321 traffic analysis zones (TAZ) in Shiraz, mobile phone data was collected over a one-week period (from 2021-06-24 to 2021-06-30). Following the implementation of data cleaning and preprocessing techniques,  individuals’ stay point and home locations were identified. The population of each TAZ was estimated by utilising the location of individuals within their respective homes. The estimated population and the real population in each spatial unit were employed to calculate the expansion factor. The activity levels within one-hour time intervals on workdays, semi-workdays, and weekends were estimated using an appropriate expansion factor. To examine the spatial dependency of the variable of interest (density of activities), global and local Moran’s I indices were applied to the aggregated density of activities. The study employed exploratory analysis of urban activities time series to identify the trend of activity level, peak periods, intensity change by time, as well as other relevant temporal characteristics. Additionally, the Standardized Normal Homogeneity Test (SNHT) was employed to identify the change point of activity in time series, which indicates the commencement of the activities.

The results not only demonstrated a significant positive spatial autocorrelation of the density of activities within traffic zones (P-Value < 0.001), but also identified the hotspots in the central parts of the study areas. It is notable that the central zones of the city exhibited high activity density, which was influenced by the spatial relationships within the study area. An exploratory analysis of time series revealed variations in activity patterns. These patterns exhibited higher activity levels on workdays compared to semi-workdays, and weekends. The time series observed in the latter half of the semi-workdays exhibited a striking resemblance to that of workdays, yet subsequently exhibited a trend between workdays and non-workdays as the activity level decreased. By examining the time series of activities, it can be observed that the mid-day peak period occurs at 12:00 to 14:00, while the evening peak period occurs at 20:00 to 22:00. Additionally, the lowest level of daily activity was identified between 3 and 6 a.m. The time series uniformity test was employed to ascertain the starting times of activities on workdays and semi-workdays, which were identified as 8:00 am, and on weekends, which were identified as 9:00 am. To validate the detected population and expansion factors and thus the estimated activity level, a spatial correlation between the estimated mobile phone population and the actual population within traffic analysis zones was calculated, which yielded an approximately 82% correlation coefficient. This correlation is statistically significant and therefore acceptable.

The results of these analyses could prove beneficial for the formulation of appropriate transportation planning and policy, as well as for the management of population density at hotspots at any time of the day. Furthermore, they could inform the analysis of urban transportation environmental impacts. With the availability of accurate mobile phone data for a range of spatial units, including traffic zones and even entire countries, it is possible to extract a diverse range of urban activity patterns, including those highlighted in this research.

Air pollution represents one of the most important challenges currently facing the majority of countries, largely as a consequence of the advancement of industry and technology. . It is evident that the country of Iran, and in particular  the city of Tehran, is not exempt from this phenomenon. The impact of urban air pollution on the environment and human health has raised increasing concerns among researchers, policy makers, and citizens. In order to minimize  the adverse effects on human health, it is of paramount importance to monitor  air pollution at high temporal and spatial resolution. On the other hand, air pollution measurement stations in the urban areas, despite their high accuracy in pollutant measurement, are not generalisable due to temporal and spatial limitations and point measurement. An alternative solution is the use of remote sensing and satellite data, which is a suitable method for monitoring air pollution due to the optimal cost and wide coverage. Nitrogen dioxide (NO2) and ozone (O3) pollutants are among the most important indicators of air pollution. Therefore, the objective of this research,  is to develop a for the  concentration distribution of these pollutants inTehran with an equal spatial resolution (approximately one kilometer) and a higher level of accuracy than satellite data.

In order to model the concentration distribution of two pollutants, NO2 and O3, with appropriate accuracy and resolution, an innovative method based on the kriging interpolation method has been  employed. This modeling method has been developed by simultaneously utilizing the advantages of both pollution measurement station data and high resolution Sentinel-5P satellite data. The former comprises 21 active air pollution measurement stations that have been identified as offering the highest accuracy in measuring parameters in different parts of Tehran. The Google Earth Engine system, has been employed to generate concentration distribution maps of the two pollutants in all 22 districts of Tehran on a monthly basis. Additionally, the system has been used to generate point satellite data of the two pollutants in the spatial coordinates of the ground stations on an hourly, daily and monthly basis. The data was prepared and collected in the Google Earth system over the course of one year, from 1 April 1400 to 1 April 1401. Following the correlation between the satellite data and the ground measurement station data and removal of the bias from the satellite data, different stages of innovative kriging interpolation modeling were employed to model the concentration distribution of the two parameters.

In order to validate the output data from pollutant distribution modeling, 70% of the stations were selected as training data (Train) and 30% of the stations were selected as test data (Test). The points were randomly selected for each month of the year. The final modeling of pollutant distribution was conducted using the training data with the model subsequently validated using the test data. Validation was conducted using both the average error between the predicted data by the model and the station data extracted from the Tehran Air Quality Control Company (in ppb units) and also calculating the RMSE index. The results demonstarte that the average monthly error of the proposed model has decreased from 16.8 to 1.73% for NO2 pollutant and from 21.9 to 2.53% for O3 pollutant compared to the data of the Steinel 5P satellite. Additionally, the root mean square error (RMSE) of this model is equal to 2.79 ppb and 0.86 ppb for NO2 and O3 pollutant, respectively. In a comparable scenario, the RMSE index of the Sentinel 5P satellite output map in relation to the pollution measurement station data for NO2 and O3 pollutants is 10.083 ppb and 6.238 ppb, respectively.

Considering that the proposed integrated model has performed very well in modeling the concentration distribution of the two pollutants throughout the year with an accuracy and spatial resolution of almost one kilometer, it is recommended that the simultaneous use of satellite and ground data be employed in the estimation of pollutants.

The challenges of urban life, such as the reduction of the environment's role as a space for citizens' presence and physical activity, the increase in vehicle usage, and the resultant inactivity and rise in non-communicable diseases, have raised global concerns about public health. This research aims to evaluate both subjectively and objectively the environmental criteria affecting the general health of residents in three dimensions: physical, psychological, and social, within the Agha Zaman neighborhood of Sanandaj city.

The collection of subjective and objective research data was conducted sequentially. The research was divided into four phases. The first phase involved a subjective qualitative assessment of residents regarding their mental and social health. The second phase involved collecting quantitative subjective data about residents' physical health. The third phase was a quantitative objective assessment of the environment. The fourth phase examined the correlation between the research variables. Subjective data were obtained using a questionnaire, while objective data were gathered using a geographic information system (GIS). Regression analysis in SPSS software was used to analyze the relationship between neighborhood environmental criteria and physical activities, and to determine the relationship between variables. Objective data, such as the type of block arrangement, spatial pattern of the neighborhood, land use layer, and road network, were calculated using GIS and entered into the space syntax index to determine the neighborhood's pedestrianization. Finally, the relationships and effects of environmental criteria on public health were identified using regression analysis in Lisrel software.

The results showed that environmental comfort and tranquility, with a score of 23, and social interactions and neighborhood culture, with a score of 21, have the greatest impact on mental and social health, respectively. Additionally, environmental criteria such as a mix of uses (score: 5.671), visual and aesthetic qualities (score: 7.961), and special infrastructure for pedestrians and bicycles (score: 8.475) have the most significant impact on physical work, leisure, and sports activities. Consequently, these criteria influence physical health. According to the data, Namaki Street, with a score of 21, has the highest level of connectivity, interconnection, depth, and control within the neighborhood, leading to the highest level of pedestrian circulation.

The overall results indicate that due to the direct impact and relationship of urban design environmental criteria on physical activities, and the positive and meaningful relationship between physical activities and general health, it is evident that the general health of residents is related to the environmental criteria of urban design. However, this relationship is mediated by physical activities.

In recent years, global population growth and urban expansion have led to significant land use and cover changes. These changes have numerous detrimental consequences, such as increasing surface temperatures, deforestation, desertification, degradation of ecosystem services, biodiversity loss, and threats to food security. Therefore, monitoring and modeling these changes are essential for optimal land management and sustainable utilization of natural resources. Given that the Aras River Basin has undergone significant transformations over time, particularly in built-up land developments, this research focuses on modeling land use/land cover changes in this area.                  

Initially, land use maps for the region were extracted for the years 2000 and 2020 from the Globeland30 project of the China National Geomatics Center. Subsequently, two maps were prepared to illustrate the potential growth of built-up land based on a land development scenario. This was achieved using advanced decision-making analysis methods based on GIS, including BWM and MEREC. Finally, these two maps, along with the land use maps, were combined to form the input for the CA-Markov model. The modeling process was carried out twice: once using the BWM + CA-Markov combination, and again using the CA-Markov + MEREC combination for the year 2040. 

The examination of the results demonstrated that in the output of the combined BWM + CA-Markov model, the extent of built-up land increased from 603 square kilometers in 2020 to over 930 square kilometers in 2040. Meanwhile, this figure was approximately 829 square kilometers in the output of the MEREC + CA-Markov model. Furthermore, the final results obtained from the intersection of these combined models also indicated an increase in the extent of this land from 603 square kilometers in 2020 to 930 square kilometers in 2040.

The continuous growth of built-up land in this basin can lead to the destruction of environmental resources and pose threats to ecosystems. The findings of this study provide relevant managers with valuable insights for optimal management of future conditions and the provision of necessary infrastructure.

Intelligent emergency response systems utilize modern technologies such as the Internet of Things (IoT) to enhance the performance of emergency response units. These systems are designed to improve service quality, reduce costs, and increase monitoring of the emergency response process. Key objectives include optimizing emergency response routes through communication with objects and collecting spatial data. Utilizing IoT-based routing models enables optimizing emergency response routes and enhancing the overall user experience. In essence, these systems leverage data collected by IoT to enhance the emergency response process. Intelligent emergency response systems play a crucial role in improving the efficiency of emergency response units and elevating service levels in emergencies. These systems are readily available and enhance productivity and efficiency in emergencies.

A spatial data infrastructure has been developed to integrate the system and enhance emergency response efforts, providing critical capabilities for improving emergency medical services. This infrastructure includes a portal that accurately displays the optimal route from the incident location to the medical center on a map, assisting the medical team in quickly and efficiently reaching the injured individual. Additionally, this portal enables the transfer of sensor information, such as vital signs of the injured person, to the physician's mobile phone in the ambulance via Bluetooth. This allows the information to be shared simultaneously for further assessment, enabling quick and accurate assistance in emergencies. This system increases efficiency and speed in responding to emergencies, providing rapid and optimal access to medical services. In summary, this spatial data infrastructure has significantly improved the performance of emergency medical response and facilitated the delivery of enhanced and optimized services in emergencies.

Medical centers prioritize healthcare and treatment. They employ an online hierarchical weighting model to ascertain these priorities and enhance the efficiency of resource allocation processes. This model helps optimize resource allocation based on real-time health information of the injured individuals. In a trial case, an injured person was successfully treated in District 5 of Tehran. The efficient use of IoT and spatial data infrastructure enabled this medical center to enhance and optimize its healthcare services. These findings underscore the significance of integrating spatial information, medical data, and IoT technology to advance healthcare services and elevate the quality of treatment.

Traditional emergency response systems operate primarily based on outdated mechanisms and lack modern technologies, including IoT and spatial data integration. Consequently, these systems may encounter challenges such as delays in dispatching emergency personnel to the incident location and a lack of accurate and rapid patient information. Incorporating modern technologies like artificial intelligence, IoT, and geographic information systems can address the challenges faced by traditional emergency response systems. These technologies enable faster and more efficient crisis responses and assist organizations, such as crisis management agencies, in making better resource allocation decisions during emergencies, thereby improving overall performance. By utilizing data collected through these technologies, emergency organizations can significantly enhance their response to emergencies, reducing time, financial, and human costs. Overall, this new approach to emergency response systems enables better adaptability in facing various crises and improves emergency response efficiency.